x86-lnxa.s 5.4 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282
	.file	"bn_mulw.c"
	.version	"01.01"
gcc2_compiled.:
.text
	.align 4
.globl _bn_mul_add_word
	.type	 _bn_mul_add_word,@function
_bn_mul_add_word:
	pushl %ebp
	pushl %edi
	pushl %esi
	pushl %ebx

	# ax		L(t)
	# dx		H(t)
	# bx		a
	# cx		w
	# di		r
	# si		c
	# bp		num
	xorl %esi,%esi		# c=0
	movl 20(%esp),%edi	# r => edi
	movl 24(%esp),%ebx	# a => exb
	movl 32(%esp),%ecx	# w => ecx
	movl 28(%esp),%ebp	# num => ebp

	shrl $2,%ebp		# num/4
	je .L910

#	.align 4
.L110:
	# Round 1
	movl %ecx,%eax		# w => eax
	mull (%ebx)		# w * *a 
	addl (%edi),%eax	# *r+=L(t)
	adcl $0,%edx		# H(t)+= carry
	addl %esi,%eax		# L(t)+=c
	adcl $0,%edx		# H(t)+=carry
	movl %eax,(%edi)	# *r+=L(t)
	movl %edx,%esi		# c=H(t)

	# Round 2
	movl %ecx,%eax		# w => eax
	mull 4(%ebx)		# w * *a 
	addl 4(%edi),%eax	# *r+=L(t)
	adcl $0,%edx		# H(t)+= carry
	addl %esi,%eax		# L(t)+=c
	adcl $0,%edx		# H(t)+=carry
	movl %eax,4(%edi)	# *r+=L(t)
	movl %edx,%esi		# c=H(t)

	# Round 3
	movl %ecx,%eax		# w => eax
	mull 8(%ebx)		# w * *a 
	addl 8(%edi),%eax	# *r+=L(t)
	adcl $0,%edx		# H(t)+=carry
	addl %esi,%eax		# L(t)+=c
	adcl $0,%edx		# H(t)+=carry
	movl %eax,8(%edi)	# *r+=L(t)
	movl %edx,%esi		# c=H(t)

	# Round 4
	movl %ecx,%eax		# w => eax
	mull 12(%ebx)		# w * *a 
	addl 12(%edi),%eax	# *r+=L(t)
	adcl $0,%edx		# H(t)+=carry
	addl %esi,%eax		# L(t)+=c
	adcl $0,%edx		# H(t)+=carry
	movl %eax,12(%edi)	# *r+=L(t)
	movl %edx,%esi		# c=H(t)

	addl $16,%ebx		# a+=4 (4 words)
	addl $16,%edi		# r+=4 (4 words)

	decl %ebp		# --num
	je .L910
	jmp .L110
#	.align 4
.L910:
	movl 28(%esp),%ebp	# num => ebp
	andl $3,%ebp
	je .L111

	# Round 1
	movl %ecx,%eax		# w => eax
	mull (%ebx)		# w * *a 
	addl (%edi),%eax	# *r+=L(t)
	adcl $0,%edx		# H(t)+=carry
	addl %esi,%eax		# L(t)+=c
	adcl $0,%edx		# H(t)+=carry
	movl %eax,(%edi)	# *r+=L(t)
	movl %edx,%esi		# c=H(t)
	decl %ebp		# --num
	je .L111

	# Round 2
	movl %ecx,%eax		# w => eax
	mull 4(%ebx)		# w * *a 
	addl 4(%edi),%eax	# *r+=L(t)
	adcl $0,%edx		# H(t)+=carry
	addl %esi,%eax		# L(t)+=c
	adcl $0,%edx		# H(t)+=carry
	movl %eax,4(%edi)	# *r+=L(t)
	movl %edx,%esi		# c=H(t)
	decl %ebp		# --num
	je .L111

	# Round 3
	movl %ecx,%eax		# w => eax
	mull 8(%ebx)		# w * *a 
	addl 8(%edi),%eax	# *r+=L(t)
	adcl $0,%edx		# H(t)+=carry
	addl %esi,%eax		# L(t)+=c
	adcl $0,%edx		# H(t)+=carry
	movl %eax,8(%edi)	# *r+=L(t)
	movl %edx,%esi		# c=H(t)

#	.align 4
.L111:
	movl %esi,%eax		# return(c)
	popl %ebx
	popl %esi
	popl %edi
	popl %ebp
	ret
.Lfe1:
	.size	 _bn_mul_add_word,.Lfe1-_bn_mul_add_word
	.align 4
.globl _bn_mul_word
	.type	 _bn_mul_word,@function
_bn_mul_word:
	pushl %ebp
	pushl %edi
	pushl %esi
	pushl %ebx

	# ax		L(t)
	# dx		H(t)
	# bx		a
	# cx		w
	# di		r
	# num		bp
	# si		c
	xorl %esi,%esi		# c=0
	movl 20(%esp),%edi	# r => edi
	movl 24(%esp),%ebx	# a => exb
	movl 28(%esp),%ebp	# num => bp
	movl 32(%esp),%ecx	# w => ecx

#	.align 4
.L210:
	movl %ecx,%eax		# w => eax
	mull (%ebx)		# w * *a 
	addl %esi,%eax		# L(t)+=c
	adcl $0,%edx		# H(t)+=carry
	movl %eax,(%edi)	# *r=L(t)
	movl %edx,%esi		# c=H(t)
	decl %ebp		# --num
	je .L211

	movl %ecx,%eax		# w => eax
	mull 4(%ebx)		# w * *a 
	addl %esi,%eax		# L(t)+=c
	adcl $0,%edx		# H(t)+=carry
	movl %eax,4(%edi)	# *r=L(t)
	movl %edx,%esi		# c=H(t)
	decl %ebp		# --num
	je .L211

	movl %ecx,%eax		# w => eax
	mull 8(%ebx)		# w * *a 
	addl %esi,%eax		# L(t)+=c
	adcl $0,%edx		# H(t)+=carry
	movl %eax,8(%edi)	# *r=L(t)
	movl %edx,%esi		# c=H(t)
	decl %ebp		# --num
	je .L211

	movl %ecx,%eax		# w => eax
	mull 12(%ebx)		# w * *a 
	addl %esi,%eax		# L(t)+=c
	adcl $0,%edx		# H(t)+=carry
	movl %eax,12(%edi)	# *r=L(t)
	movl %edx,%esi		# c=H(t)
	decl %ebp		# --num
	je .L211

	addl $16,%ebx		# a+=4 (4 words)
	addl $16,%edi		# r+=4 (4 words)

	jmp .L210
#	.align 4
.L211:
	movl %esi,%eax		# return(c)
	popl %ebx
	popl %esi
	popl %edi
	popl %ebp
	ret
.Lfe2:
	.size	 _bn_mul_word,.Lfe2-_bn_mul_word

	.align 4
.globl _bn_sqr_words
	.type	 _bn_sqr_words,@function
_bn_sqr_words:
	pushl %edi
	pushl %esi
	pushl %ebx
	movl 16(%esp),%esi	# r
	movl 20(%esp),%edi	# a
	movl 24(%esp),%ebx	# n
#	.align 4
	shrl $2,%ebx
	jz .L99
.L28:
	movl (%edi),%eax	# get a
	mull %eax		# a*a
	movl %eax,(%esi)	# put low into return addr
	movl %edx,4(%esi)	# put high into return addr

	movl 4(%edi),%eax	# get a
	mull %eax		# a*a
	movl %eax,8(%esi)	# put low into return addr
	movl %edx,12(%esi)	# put high into return addr

	movl 8(%edi),%eax	# get a
	mull %eax		# a*a
	movl %eax,16(%esi)	# put low into return addr
	movl %edx,20(%esi)	# put high into return addr

	movl 12(%edi),%eax	# get a
	mull %eax		# a*a
	movl %eax,24(%esi)	# put low into return addr
	movl %edx,28(%esi)	# put high into return addr

	addl $16,%edi
	addl $32,%esi
	decl %ebx		# n-=4;
	jz .L99
	jmp .L28
#	.align 4
.L99:
	movl 24(%esp),%ebx	# n
	andl $3,%ebx
	jz .L29
	movl (%edi),%eax	# get a
	mull %eax		# a*a
	movl %eax,(%esi)	# put low into return addr
	movl %edx,4(%esi)	# put high into return addr
	decl %ebx		# n--;
	jz .L29
	movl 4(%edi),%eax	# get a
	mull %eax		# a*a
	movl %eax,8(%esi)	# put low into return addr
	movl %edx,12(%esi)	# put high into return addr
	decl %ebx		# n--;
	jz .L29
	movl 8(%edi),%eax	# get a
	mull %eax		# a*a
	movl %eax,16(%esi)	# put low into return addr
	movl %edx,20(%esi)	# put high into return addr

.L29:
	popl %ebx
	popl %esi
	popl %edi
	ret
.Lfe3:
	.size	 _bn_sqr_words,.Lfe3-_bn_sqr_words

	.align 4
.globl _bn_div64
	.type	 _bn_div64,@function
_bn_div64:
	movl 4(%esp),%edx	# a
	movl 8(%esp),%eax	# b
	divl 12(%esp)		# ab/c
	ret
.Lfe4:
	.size	 _bn_div64,.Lfe4-_bn_div64
	.ident	"GCC: (GNU) 2.6.3"